Computer Science – Computation and Language
Scientific paper
2000-03-30
Computer Science
Computation and Language
12 pages, 3 figures, Philosophical Transactions of the Royal Society of London, series A: Mathematical, Physical and Engineeri
Scientific paper
10.1098/rsta.2000.0587
This paper discusses the development of trainable statistical models for extracting content from television and radio news broadcasts. In particular we concentrate on statistical finite state models for identifying proper names and other named entities in broadcast speech. Two models are presented: the first represents name class information as a word attribute; the second represents both word-word and class-class transitions explicitly. A common n-gram based formulation is used for both models. The task of named entity identification is characterized by relatively sparse training data and issues related to smoothing are discussed. Experiments are reported using the DARPA/NIST Hub-4E evaluation for North American Broadcast News.
Gotoh Yoshihiko
Renals Steve
No associations
LandOfFree
Information Extraction from Broadcast News does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Information Extraction from Broadcast News, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Information Extraction from Broadcast News will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-201644